安装 Steam
登录
|
语言
繁體中文（繁体中文）
日本語（日语）
한국어（韩语）
ไทย（泰语）
български（保加利亚语）
Čeština（捷克语）
Dansk（丹麦语）
Deutsch（德语）
English（英语）
Español-España（西班牙语 - 西班牙）
Español - Latinoamérica（西班牙语 - 拉丁美洲）
Ελληνικά（希腊语）
Français（法语）
Italiano（意大利语）
Bahasa Indonesia（印度尼西亚语）
Magyar（匈牙利语）
Nederlands（荷兰语）
Norsk（挪威语）
Polski（波兰语）
Português（葡萄牙语 - 葡萄牙）
Português-Brasil（葡萄牙语 - 巴西）
Română（罗马尼亚语）
Русский（俄语）
Suomi（芬兰语）
Svenska（瑞典语）
Türkçe（土耳其语）
Tiếng Việt（越南语）
Українська（乌克兰语）
报告翻译问题
0 
举报此帖
To get to EchoColony's mod options, you need to go to Options>find or search for EchoColony and input the info.
The image below was actually posted by the mod author. Local Model Endpoint has to be what is typed. The second line is whatever model you are using. After loading your model in LM Studio let it load then increase the context length to at least 7,000 then reload.
I would suggest a bare minimum of 32 gb of ram, even though with the 1.6 update your ram usage can balloon and slow down your pc, you also want to close any and all browsers ect.... before using LM Studio or it may stall out.
I learned all this by trial and error, I still have no clue what the other half of LM Studio does. I used images since I didn't want to type a wall of text and having an image guide might help others since having pictures to show exactly what is being done helps a bunch.
Hope this helps somewhat. BTW some models do not work well with LM Studio, neuraldaredevel seems to work fairly well and the larger models need a bigger gpu, at minimum a 6 gb card might work but I strongly suggest an 8gb card or higher.
https://imgur.com/4J6N0TY